ImgTrojan: Jailbreaking Vision-Language Models with ONE Image

作者：Xijia Tao, Shuai Zhong, Lei Li, Qi Liu, Lingpeng Kong · 年份：2025 · DOI：10.18653/v1/2025.naacl-long.360 · 被引用次数：8 · 研究领域：Digital Media Forensic Detection、Adversarial Robustness in Machine Learning、Law in Society and Culture

Xijia Tao, Shuai Zhong, Lei Li, Qi Liu, Lingpeng Kong. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.